Fix CI and other issues

.github/workflows/benchmark.yml

@@ -23,7 +23,7 @@ jobs:
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: "3.11"
       - name: Install dependencies
         run: |
           sudo apt update -y

.github/workflows/build-gpu.yml

@@ -17,7 +17,7 @@ jobs:
         shell: bash -l {0}
     strategy:
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/build.yml

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11", "3.12"]
+        python-version: ["3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v4

.github/workflows/upstream.yml

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11"]
+        python-version: ["3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v4

.github/workflows/wheels.yml

@@ -18,7 +18,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
 
     steps:
     - uses: actions/checkout@v4
@@ -46,7 +46,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest]
-        python-version: ["3.10", "3.11"]
+        python-version: ["3.11", "3.12"]
     runs-on: ${{ matrix.os }}
     steps:
       # checkout repo to subdirectory to get access to scripts
@@ -76,7 +76,7 @@ jobs:
     needs: ['build']
     strategy:
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
     steps:
       # checkout repo to subdirectory to get access to scripts
       - uses: actions/checkout@v4

.github/workflows/windows.yml

@@ -14,7 +14,7 @@ jobs:
     runs-on: windows-latest
     strategy:
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
 
     steps:
     - uses: actions/checkout@v4
@@ -30,8 +30,8 @@ jobs:
       shell: bash -l {0}
       # conda can't install all dev tools, so we need to split it between conda and pip
       run: |
-        conda install --file requirements.txt msprime
-        pip install -r requirements-dev.txt
+        conda install msprime
+        pip install -r requirements.txt -r requirements-dev.txt
     - name: Test with pytest
       # activate conda
       shell: bash -l {0}

.mergify.yml

@@ -2,9 +2,9 @@ queue_rules:
   - name: default
     conditions:
       - base=main
-      - status-success=build (3.10)
       - status-success=build (3.11)
-      - status-success=win_build (3.10)
+      - status-success=build (3.12)
+      - status-success=win_build (3.11)
       - approved-reviews-by=@sgkit-dev/committers
       - "#approved-reviews-by>=1"
       - label=auto-merge
@@ -13,9 +13,9 @@ pull_request_rules:
   - name: automatic merge
     conditions:
       - base=main
-      - status-success=build (3.10)
       - status-success=build (3.11)
-      - status-success=win_build (3.10)
+      - status-success=build (3.12)
+      - status-success=win_build (3.11)
       - approved-reviews-by=@sgkit-dev/committers
       - "#approved-reviews-by>=1"
       - label=auto-merge

docs/conf.py

@@ -60,12 +60,19 @@
     *[p.stem for p in (HERE / "extensions").glob("*.py")],
 ]
 
+# Prefer PEP 604 union syntax (X | Y) to avoid unresolved typing.Union references.
+always_use_bars_union = True
+
 # Enable math notation in mystnb
 myst_enable_extensions = [
     "amsmath",
     "dollarmath",
 ]
 
+# Temporary disable notebook execution during docs build (see issue #1332):
+# https://github.com/sgkit-dev/sgkit/issues/1332
+nb_execution_mode = "off"
+
 extlinks = {
     "issue": ("https://github.com/sgkit-dev/sgkit/issues/%s", "GH %s"),
     "pr": ("https://github.com/sgkit-dev/sgkit/pull/%s", "PR %s"),
@@ -123,7 +130,7 @@ def filter(self, record: pylogging.LogRecord) -> bool:
 
 intersphinx_mapping = dict(
     dask=("https://docs.dask.org/en/stable/", None),
-    xarray=("https://xarray.pydata.org/en/stable/", None),
+    xarray=("https://docs.xarray.dev/en/stable/", None),
     zarr=("https://zarr.readthedocs.io/en/stable", None),
     numpy=("https://numpy.org/doc/stable/", None),
     python=("https://docs.python.org/3", None),

docs/getting_started.rst

@@ -10,7 +10,7 @@ Getting Started
 Installation
 ------------
 
-You can install sgkit with pip. Python 3.10, 3.11, or 3.12 is required::
+You can install sgkit with pip. Python 3.11 or 3.12 is required::
 
     $ pip install sgkit
 

pyproject.toml

@@ -14,23 +14,23 @@ classifiers = [
   "Intended Audience :: Science/Research",
   "Programming Language :: Python",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Topic :: Scientific/Engineering",
 ]
 urls = { Homepage = "https://github.com/sgkit-dev/sgkit" }
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 dependencies = [
-  "numpy < 2.2",
+  "numpy >= 2.3.5; sys_platform == \"darwin\"", # Apple ARM chip error
+  "numpy >= 2.0; sys_platform != \"darwin\"",
   "xarray < 2025.03.1",
   "dask[array,dataframe] >= 2022.01.0, <= 2024.8.0",
   "scipy < 1.16",
   "zarr >= 2.10.0, != 2.11.0, != 2.11.1, != 2.11.2, < 3",
   "numba",
   "fsspec != 2021.6.*",
   "scikit-learn",
-  "pandas",
+  "pandas < 3.0",
   "setuptools >= 41.2",                                   # For pkg_resources
 ]
 dynamic = ["version"]
@@ -69,7 +69,7 @@ fail_under = 100
 
 [tool.pytest.ini_options]
 addopts = "--doctest-modules --ignore=validation --cov-fail-under=100"
-norecursedirs = [".eggs", "build", "docs"]
+norecursedirs = [".eggs", "build", "docs", ".hypothesis"]
 filterwarnings = ["error", "ignore::DeprecationWarning"]
 
 

requirements-doc.txt

@@ -1,7 +1,7 @@
 myst_nb
 pydata-sphinx-theme
-sphinx==6.2.1
-sphinx_autodoc_typehints>=1.14.0
+sphinx < 9.0.0
+sphinx_autodoc_typehints
 sphinx-copybutton
 scanpydoc
 ipython

requirements.txt

@@ -1,9 +1,10 @@
-numpy < 2.2
+numpy >= 2.3.5; sys_platform == "darwin"
+numpy >= 2.0; sys_platform != "darwin"
 xarray < 2025.03.1
 dask[array,dataframe] >= 2023.01.0, <= 2024.8.0
 scipy < 1.16
 numba
 zarr >= 2.10.0, != 2.11.0, != 2.11.1, != 2.11.2, < 3
 fsspec != 2021.6.*
 scikit-learn
-pandas
+pandas < 3.0

sgkit/tests/io/test_dataset.py

@@ -58,7 +58,7 @@ def test_save_unequal_chunks_error():
     # Normal zarr errors shouldn't be caught
     with pytest.raises(
         (FileExistsError, ValueError),
-        match="(path '' contains an array|is not empty)",
+        match="(path '' contains an array|is not empty|contains data)",
     ):
         save_dataset(ds, {".zarray": ""})
 

sgkit/tests/test_association.py

@@ -254,7 +254,11 @@ def run(traits: Sequence[str]) -> Dataset:
 
     traits = [f"trait_{i}" for i in range(ds.attrs["n_trait"])]
     # Run regressions on individual traits and concatenate resulting statistics
-    dfr_single = xr.concat([run([t]) for t in traits], dim="traits").to_dataframe()
+    dfr_single = xr.concat(
+        [run([t]) for t in traits],
+        dim="traits",
+        data_vars="all",
+    ).to_dataframe()
     # Run regressions on all traits simulatenously
     dfr_multi: DataFrame = run(traits).to_dataframe()
     pd.testing.assert_frame_equal(dfr_single, dfr_multi)

sgkit/tests/test_distance.py

@@ -143,6 +143,9 @@ def test_distance_ndarray() -> None:
         pytest.param("correlation", correlation, "i8", "gpu", marks=pytest.mark.gpu),
     ],
 )
+@pytest.mark.filterwarnings(
+    "ignore:invalid value encountered in correlation_reduce_cpu:RuntimeWarning"
+)
 def test_missing_values(
     metric: MetricTypes,
     metric_func: typing.Callable[[ArrayLike, ArrayLike], np.float64],

sgkit/tests/test_testing.py

@@ -10,6 +10,9 @@
 @pytest.mark.filterwarnings(
     "ignore::UserWarning"
 )  # codec `vlen-utf8` not in Zarr v3 spec`
+@pytest.mark.filterwarnings(
+    "ignore:The data type .* does not have a Zarr V3 specification.*"
+)
 def test_simulate_genotype_call_dataset__zarr(tmp_path):
     path = str(tmp_path / "ds.zarr")
     ds = simulate_genotype_call_dataset(n_variant=10, n_sample=10)